List the most recent local agent sessions across Claude Code, Codex, Gemini, OpenClaw, and Hermes, newest first. Use to find a session to inspect.
AI agents call list_recent_sessions to retrieve information from AgentWatch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays session information across multiple agent platforms. It performs no writes, deletes, executions, or financial operations. The data returned is local agent session metadata (timestamps, identifiers, and related telemetry), which poses minimal risk even if misused by an AI agent.
From the tool's definition Tool description states 'List the most recent local agent sessions' — a query operation that retrieves session metadata without modification. The verb 'list' and phrase 'to find a session to inspect' indicate read-only browsing of historical data.
Documented attack patterns abuse exactly the kind of access list_recent_sessions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AgentWatch, and nothing reaches the server without passing your rules. This is the rule we recommend for list_recent_sessions:
{
"version": "1",
"default": "deny",
"tools": {
"list_recent_sessions": {}
}
}list_recent_sessions is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List the most recent local agent sessions across Claude Code, Codex, Gemini, OpenClaw, and Hermes, newest first. Use to find a session to inspect. It is categorised as a Read tool in the AgentWatch MCP Server, which means it retrieves data without modifying state.
Register the AgentWatch MCP server in PolicyLayer and add a rule for list_recent_sessions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches AgentWatch. Nothing to install.
list_recent_sessions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_recent_sessions rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_recent_sessions. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_recent_sessions is provided by the AgentWatch MCP server (mishanefedov/agentwatch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AgentWatch, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 AgentWatch tools catalogued and risk-classified — across an index of 43,000+ MCP servers.